Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1234 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0442. Min Act: -0.0003

Data Index: 1588698 (Python Code)

Max Activating Token Index: 257

Text #1

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0437. Min Act: -0.0003

Data Index: 1536511 (Python Code)

Max Activating Token Index: 151

Text #2

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0424. Min Act: -0.0003

Data Index: 1417422 (Python Code)

Max Activating Token Index: 163

Text #3

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0415. Min Act: -0.0003

Data Index: 1405873 (Python Code)

Max Activating Token Index: 361

Text #4

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0412. Min Act: -0.0003

Data Index: 170189 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0420. Min Act: -0.0003

Data Index: 1624712 (Python Code)

Max Activating Token Index: 964

Text #6

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0413. Min Act: -0.0004

Data Index: 260366 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0429. Min Act: -0.0003

Data Index: 1462148 (Python Code)

Max Activating Token Index: 901

Text #8

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0399. Min Act: -0.0003

Data Index: 1215316 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0410. Min Act: -0.0003

Data Index: 1528306 (Python Code)

Max Activating Token Index: 780

Text #10

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0407. Min Act: -0.0003

Data Index: 1625156 (Python Code)

Max Activating Token Index: 517

Text #11

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0388. Min Act: -0.0004

Data Index: 304665 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0395. Min Act: -0.0003

Data Index: 530369 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0393. Min Act: -0.0003

Data Index: 1299462 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0394. Min Act: -0.0003

Data Index: 1398461 (Python Code)

Max Activating Token Index: 383

Text #15

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0394. Min Act: -0.0003

Data Index: 1431526 (Python Code)

Max Activating Token Index: 143

Text #16

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0392. Min Act: -0.0003

Data Index: 892754 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0383. Min Act: -0.0003

Data Index: 802342 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0386. Min Act: -0.0003

Data Index: 1584703 (Python Code)

Max Activating Token Index: 608

Text #19

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0391. Min Act: -0.0003

Data Index: 290077 (C4 (Web Text))

Max Activating Token Index: 303